Counterfactual explanations and how to find them: literature review and benchmarking
R Guidotti - Data Mining and Knowledge Discovery, 2022 - Springer
Interpretable machine learning aims at unveiling the reasons behind predictions returned by
uninterpretable classifiers. One of the most valuable types of explanation consists of …
uninterpretable classifiers. One of the most valuable types of explanation consists of …
From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable ai
The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …
black boxes raised the question of how to evaluate explanations of machine learning (ML) …
Deep neural networks and tabular data: A survey
Heterogeneous tabular data are the most commonly used form of data and are essential for
numerous critical and computationally demanding applications. On homogeneous datasets …
numerous critical and computationally demanding applications. On homogeneous datasets …
Openxai: Towards a transparent evaluation of model explanations
While several types of post hoc explanation methods have been proposed in recent
literature, there is very little work on systematically benchmarking these methods. Here, we …
literature, there is very little work on systematically benchmarking these methods. Here, we …
A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence
A number of algorithms in the field of artificial intelligence offer poorly interpretable
decisions. To disclose the reasoning behind such algorithms, their output can be explained …
decisions. To disclose the reasoning behind such algorithms, their output can be explained …
Benchmarking and survey of explanation methods for black box models
The rise of sophisticated black-box machine learning models in Artificial Intelligence
systems has prompted the need for explanation methods that reveal how these models work …
systems has prompted the need for explanation methods that reveal how these models work …
Counterfactuals and causability in explainable artificial intelligence: Theory, algorithms, and applications
Deep learning models have achieved high performance across different domains, such as
medical decision-making, autonomous vehicles, decision support systems, among many …
medical decision-making, autonomous vehicles, decision support systems, among many …
Counterfactual explanations can be manipulated
D Slack, A Hilgard, H Lakkaraju… - Advances in neural …, 2021 - proceedings.neurips.cc
Counterfactual explanations are emerging as an attractive option for providing recourse to
individuals adversely impacted by algorithmic decisions. As they are deployed in critical …
individuals adversely impacted by algorithmic decisions. As they are deployed in critical …
Classification of explainable artificial intelligence methods through their output formats
Machine and deep learning have proven their utility to generate data-driven models with
high accuracy and precision. However, their non-linear, complex structures are often difficult …
high accuracy and precision. However, their non-linear, complex structures are often difficult …
Clear: Generative counterfactual explanations on graphs
Counterfactual explanations promote explainability in machine learning models by
answering the question “how should the input instance be altered to obtain a desired …
answering the question “how should the input instance be altered to obtain a desired …